Upload folder using huggingface_hub
Browse files- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/env.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/env_sv.csv +0 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/eval.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/eval_sv.csv +11 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/online_agent.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/online_agent_sv.csv +101 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_250000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_300000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_350000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_400000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_450000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_500000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_550000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_600000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_650000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_700000.pkl +3 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/progress.tk +1 -0
- O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/token.tk +1 -0
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/env.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/env_sv.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/eval.csv
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
avg_gripper_contact_length,num_gripper_contacts,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
|
| 2 |
+
0.0,0.0,-0.039599132836780015,-0.009158586246181075,-0.039177470258307104,0.019943357660774496,21.879270830708645,20.08399999999845,0.56,10369.36,-0.58,-623.06,399.68,1.3125601625442505,250000
|
| 3 |
+
0.0,0.0,-0.05259145014763751,-0.005797902910789013,-0.05230177169337176,0.004644577708589067,23.266258581510613,15.535999999999126,0.68,28903.28,-0.46,-499.12,308.72,1.0302812242507935,300000
|
| 4 |
+
0.0,0.0,-0.04094559706511066,-0.004981888833699135,-0.04011604590823396,-0.007624409475716033,27.27371513532251,15.70399999999927,0.72,44777.08,-0.36,-468.58,312.08,1.0622568178176879,350000
|
| 5 |
+
0.0,0.0,-0.031552535528182324,-0.02574896213394369,-0.03223578898236609,-0.022475621050816227,33.79749799884409,10.787999999999712,0.96,58428.9,-0.04,-315.36,213.76,0.7683788871765137,400000
|
| 6 |
+
0.0,0.0,-0.0219506925706055,-0.034828638522725296,-0.023380261265137474,-0.03876171136777367,35.375293424664996,8.530999999999793,1.0,68205.6,0.0,-244.3,168.62,0.6631070709228516,450000
|
| 7 |
+
0.0,0.0,-0.013516417041037287,-0.04395163905257297,-0.014559140243517663,-0.03787310049203143,34.610287955676476,8.57799999999976,1.0,77033.8,0.0,-245.2,169.56,0.6419641399383544,500000
|
| 8 |
+
0.0,0.0,-0.011613685930672692,-0.05284039271746012,-0.013579759385144875,-0.06427821729493656,35.84734110655382,8.235999999999736,1.0,85992.88,0.0,-238.82,162.72,0.5932840347290039,550000
|
| 9 |
+
0.0,0.0,-0.031997955617118955,-0.055030033712902895,-0.032952331199982296,-0.0660142296766323,35.81267833886971,7.178999999999645,1.0,93820.58,0.0,-205.32,141.58,0.5370694398880005,600000
|
| 10 |
+
0.0,0.0,-0.01909630834718216,-0.055141132269381304,-0.019734820769889055,-0.05553057935518585,35.33076087400875,7.5579999999996845,1.0,101305.12,0.0,-215.46,149.16,0.5706422138214111,650000
|
| 11 |
+
0.0,0.0,-0.019246554409209426,-0.05895812470492264,-0.020458019419222852,-0.06318932920365247,35.74090190911471,7.2139999999995466,1.0,108913.48,0.0,-203.34,142.28,0.5314797258377075,700000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/eval_sv.csv
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
avg_gripper_contact_length,num_gripper_contacts,prev_qpos,prev_qvel,qpos,qvel,control,time,success,total.timesteps,episode.final_reward,episode.return,episode.length,episode.duration,step
|
| 2 |
+
0.0,0.0,-0.039599132836780015,-0.009158586246181075,-0.039177470258307104,0.019943357660774496,21.879270830708645,20.08399999999845,0.56,10369.36,-0.58,-623.06,399.68,1.3125601625442505,250000
|
| 3 |
+
0.0,0.0,-0.05259145014763751,-0.005797902910789013,-0.05230177169337176,0.004644577708589067,23.266258581510613,15.535999999999126,0.68,28903.28,-0.46,-499.12,308.72,1.0302812242507935,300000
|
| 4 |
+
0.0,0.0,-0.04094559706511066,-0.004981888833699135,-0.04011604590823396,-0.007624409475716033,27.27371513532251,15.70399999999927,0.72,44777.08,-0.36,-468.58,312.08,1.0622568178176879,350000
|
| 5 |
+
0.0,0.0,-0.031552535528182324,-0.02574896213394369,-0.03223578898236609,-0.022475621050816227,33.79749799884409,10.787999999999712,0.96,58428.9,-0.04,-315.36,213.76,0.7683788871765137,400000
|
| 6 |
+
0.0,0.0,-0.0219506925706055,-0.034828638522725296,-0.023380261265137474,-0.03876171136777367,35.375293424664996,8.530999999999793,1.0,68205.6,0.0,-244.3,168.62,0.6631070709228516,450000
|
| 7 |
+
0.0,0.0,-0.013516417041037287,-0.04395163905257297,-0.014559140243517663,-0.03787310049203143,34.610287955676476,8.57799999999976,1.0,77033.8,0.0,-245.2,169.56,0.6419641399383544,500000
|
| 8 |
+
0.0,0.0,-0.011613685930672692,-0.05284039271746012,-0.013579759385144875,-0.06427821729493656,35.84734110655382,8.235999999999736,1.0,85992.88,0.0,-238.82,162.72,0.5932840347290039,550000
|
| 9 |
+
0.0,0.0,-0.031997955617118955,-0.055030033712902895,-0.032952331199982296,-0.0660142296766323,35.81267833886971,7.178999999999645,1.0,93820.58,0.0,-205.32,141.58,0.5370694398880005,600000
|
| 10 |
+
0.0,0.0,-0.01909630834718216,-0.055141132269381304,-0.019734820769889055,-0.05553057935518585,35.33076087400875,7.5579999999996845,1.0,101305.12,0.0,-215.46,149.16,0.5706422138214111,650000
|
| 11 |
+
0.0,0.0,-0.019246554409209426,-0.05895812470492264,-0.020458019419222852,-0.06318932920365247,35.74090190911471,7.2139999999995466,1.0,108913.48,0.0,-203.34,142.28,0.5314797258377075,700000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/online_agent.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.20100777,9.409554,-69.87877,-177.8744,-204.56952,10.156871,-8.893482,140.8757,205000
|
| 3 |
+
0.2030812,13.464017,-59.740788,-176.18771,-203.49301,0.6195959,-0.47105342,63.705963,210000
|
| 4 |
+
0.17023364,12.263251,-57.90504,-174.65022,-203.8613,0.4514531,-0.46707118,38.107838,215000
|
| 5 |
+
0.18201995,15.194278,-57.595905,-175.04878,-204.4804,0.57863003,-0.5209974,45.85898,220000
|
| 6 |
+
0.21482798,10.721947,-62.788883,-174.35913,-204.68207,0.6177783,-0.49075928,42.487614,225000
|
| 7 |
+
0.1848709,22.483286,-46.073135,-174.1651,-204.51782,1.1910027,-1.0690478,65.86507,230000
|
| 8 |
+
0.18086866,11.235286,-55.918163,-172.9547,-204.68556,0.37382895,-0.39640066,41.033997,235000
|
| 9 |
+
0.22556049,10.152976,-62.81238,-173.63622,-204.3738,0.39822507,-0.37674218,37.1173,240000
|
| 10 |
+
0.17555308,9.554568,-58.444225,-172.61221,-205.03313,0.5940277,-0.5516616,37.41432,245000
|
| 11 |
+
0.20202735,13.335947,-48.50966,-172.95593,-204.98065,0.50040984,-0.4104112,44.45418,250000
|
| 12 |
+
0.18236683,15.440984,-33.451588,-170.57622,-205.1152,1.0633335,-1.2514275,50.95133,255000
|
| 13 |
+
0.21282479,12.19637,-23.920721,-171.91312,-204.80103,0.41326144,-0.5220463,64.220055,260000
|
| 14 |
+
0.18925047,10.774324,-56.61881,-171.2418,-205.19048,0.4044517,-0.37020415,44.610645,265000
|
| 15 |
+
0.18780795,18.316519,-18.646774,-165.85579,-205.13983,0.43577084,-0.44659805,47.765675,270000
|
| 16 |
+
0.20516685,14.699882,-20.07879,-168.44766,-204.37813,0.6552143,-0.7679565,52.021626,275000
|
| 17 |
+
0.19624431,14.928409,-15.76694,-169.90495,-205.11559,4.181205,-4.4612627,96.45013,280000
|
| 18 |
+
0.18718834,18.539236,-22.725163,-169.84744,-204.81511,3.5787728,-3.8363938,97.53497,285000
|
| 19 |
+
0.18884853,8.228202,-52.658596,-167.32303,-204.43582,0.40424532,-0.5250171,38.06241,290000
|
| 20 |
+
0.17194659,11.558407,-47.379284,-166.06587,-204.14784,2.6585126,-2.6177244,88.79571,295000
|
| 21 |
+
0.20329304,11.933761,-13.41958,-162.4458,-204.69919,0.44297963,-0.53581494,44.88457,300000
|
| 22 |
+
0.1613389,19.35588,-10.228258,-164.6559,-204.51425,2.1259723,-2.1698601,96.33703,305000
|
| 23 |
+
0.18891332,19.131544,-4.557439,-159.46823,-204.66443,0.4746132,-0.50542915,51.0682,310000
|
| 24 |
+
0.1632351,12.245697,1.5968426,-160.07527,-204.7615,0.4908134,-0.7087205,49.264454,315000
|
| 25 |
+
0.17598325,14.440491,-46.924316,-165.38487,-204.77924,0.8539426,-0.82388216,54.06479,320000
|
| 26 |
+
0.20054707,16.260023,-37.042057,-163.27727,-204.6969,1.0537571,-0.99057883,74.19384,325000
|
| 27 |
+
0.18412662,20.287693,-7.723515,-161.28021,-205.24512,0.6544641,-0.69861954,64.018555,330000
|
| 28 |
+
0.18113422,14.071883,2.470496,-160.15239,-204.98764,0.70118153,-0.48810682,63.532265,335000
|
| 29 |
+
0.17278692,10.066867,0.78192866,-156.50208,-204.8473,0.5756796,-0.56880754,50.4505,340000
|
| 30 |
+
0.18541476,16.935337,-15.702345,-157.31746,-204.37492,3.3171105,-2.8199182,84.433495,345000
|
| 31 |
+
0.18366764,11.666587,-22.472124,-157.97203,-204.2429,1.2402115,-1.0259283,51.13912,350000
|
| 32 |
+
0.1743964,7.1984215,-15.913654,-155.95833,-204.65659,0.68188596,-0.758972,51.007263,355000
|
| 33 |
+
0.21175303,18.841211,-20.607973,-159.5158,-205.31863,1.3890916,-1.4138421,62.24877,360000
|
| 34 |
+
0.18064243,9.564801,-3.5754108,-154.34062,-205.44847,1.2249285,-0.82055604,47.60972,365000
|
| 35 |
+
0.1740123,18.502813,-25.637144,-155.7119,-205.14563,1.4692957,-1.4782456,66.458496,370000
|
| 36 |
+
0.2098609,12.042827,-3.758899,-155.72098,-205.79437,0.90201515,-0.8859506,56.15162,375000
|
| 37 |
+
0.17615503,16.208109,4.60008,-153.68494,-205.9558,3.6985168,-3.8621852,93.64393,380000
|
| 38 |
+
0.18506245,13.661484,-24.66742,-152.11035,-204.80345,0.61868215,-0.6624401,47.13382,385000
|
| 39 |
+
0.16344944,17.388006,-14.055939,-151.01625,-204.46004,1.6258293,-1.6770139,83.659195,390000
|
| 40 |
+
0.15841107,17.616018,-17.341791,-148.30794,-203.26086,0.6245556,-0.6838363,55.242416,395000
|
| 41 |
+
0.15545848,24.551254,-9.772065,-149.55035,-204.40657,1.1222425,-1.1958777,79.06295,400000
|
| 42 |
+
0.18091281,12.180981,-5.245518,-147.90837,-203.43521,3.4111538,-3.6064765,93.27745,405000
|
| 43 |
+
0.16591415,34.31397,0.5574629,-147.49768,-204.17393,1.178774,-1.2150983,103.07872,410000
|
| 44 |
+
0.20231561,29.604925,-11.357351,-150.31169,-204.60204,1.3953775,-1.1974523,76.24299,415000
|
| 45 |
+
0.17641772,17.48673,-7.1269674,-148.88237,-204.25932,0.85872895,-0.9011842,53.958206,420000
|
| 46 |
+
0.18215272,20.720823,-6.716765,-141.95296,-200.65166,0.9066922,-0.7736609,83.27788,425000
|
| 47 |
+
0.20641512,19.810425,-4.849878,-148.29845,-204.91791,2.30933,-2.1597123,81.28222,430000
|
| 48 |
+
0.17660189,11.094462,-7.3228016,-144.80606,-203.25275,0.4992343,-0.44987458,51.339756,435000
|
| 49 |
+
0.19684954,14.5761385,3.3698266,-148.0756,-205.39117,0.6209063,-0.65316904,58.549694,440000
|
| 50 |
+
0.18752298,16.77013,-17.65461,-145.43347,-206.79004,2.0806866,-2.0905707,58.519016,445000
|
| 51 |
+
0.15905997,22.66004,-13.940053,-136.65092,-204.91208,0.68818146,-0.8356606,61.799004,450000
|
| 52 |
+
0.17852955,22.696243,-7.5126204,-146.60352,-204.16869,1.6004945,-2.0245695,106.26013,455000
|
| 53 |
+
0.20046319,12.400351,2.7658887,-143.369,-204.14307,0.6820656,-0.7226073,48.965046,460000
|
| 54 |
+
0.16603181,13.396224,-4.9958215,-145.32207,-204.59792,1.0521985,-1.1597939,56.790184,465000
|
| 55 |
+
0.19051006,22.577358,-8.894181,-145.17007,-203.70505,1.051367,-1.0433577,83.08147,470000
|
| 56 |
+
0.17710492,18.861845,-2.957842,-142.75897,-204.87173,0.95010775,-1.0798334,60.891502,475000
|
| 57 |
+
0.20014888,18.792406,-7.8571525,-145.55049,-205.05147,1.0315069,-1.1156279,76.44721,480000
|
| 58 |
+
0.14014131,13.498488,-8.811894,-141.95602,-205.03214,0.97438604,-0.95301956,60.211586,485000
|
| 59 |
+
0.16438508,17.622131,0.0073166937,-137.5183,-205.44365,1.804859,-2.7860637,75.53738,490000
|
| 60 |
+
0.16220123,18.137064,1.1836677,-138.26732,-206.47401,2.8542607,-3.1024394,92.50272,495000
|
| 61 |
+
0.1521937,13.130618,-6.0926414,-142.69913,-203.35548,0.9373735,-1.0258695,64.1406,500000
|
| 62 |
+
0.18573265,16.525612,-5.7103796,-143.23454,-204.5616,1.1768271,-1.1775948,80.72108,505000
|
| 63 |
+
0.19157785,22.621483,-7.923869,-138.0,-204.42947,1.0523185,-1.0264663,66.11385,510000
|
| 64 |
+
0.16532046,13.735717,-11.089387,-135.70116,-203.50761,0.6721011,-0.6336218,53.566017,515000
|
| 65 |
+
0.16647905,19.009996,-3.1124759,-141.74803,-202.44348,0.8190097,-1.4557772,65.08297,520000
|
| 66 |
+
0.16967948,17.789572,-8.616635,-140.17053,-204.66219,0.92178285,-1.001431,57.612152,525000
|
| 67 |
+
0.18110111,19.052444,-0.7262464,-134.04239,-204.0279,3.7241864,-3.8394585,111.93406,530000
|
| 68 |
+
0.2071534,11.235112,-6.123059,-135.75882,-205.55742,4.8970304,-4.633314,93.251205,535000
|
| 69 |
+
0.17416334,14.998515,-1.4488183,-139.46434,-200.9367,0.8948727,-0.9666061,62.150803,540000
|
| 70 |
+
0.17773488,10.925357,-17.1159,-143.5125,-203.01274,0.64000297,-0.5278116,50.071846,545000
|
| 71 |
+
0.15636533,13.704974,-4.5214024,-130.53934,-205.37036,0.57138234,-1.7236669,88.67557,550000
|
| 72 |
+
0.18564107,18.469059,-5.2898417,-138.99084,-203.01262,2.015253,-0.6794735,63.436623,555000
|
| 73 |
+
0.15758286,14.073359,-7.819827,-132.72684,-204.1892,7.0398135,-6.580752,192.36351,560000
|
| 74 |
+
0.17968695,18.241192,-5.2041836,-139.66605,-203.83383,0.63480955,-0.63171893,52.946182,565000
|
| 75 |
+
0.1725044,14.956375,2.2193115,-137.8896,-203.87447,0.40843022,-0.4981443,49.872967,570000
|
| 76 |
+
0.18485534,12.866968,0.69352674,-134.95142,-203.45863,0.7120311,-0.577571,48.615097,575000
|
| 77 |
+
0.1567674,12.027698,-3.3798804,-133.5681,-203.4459,1.2448539,-1.3802873,79.26493,580000
|
| 78 |
+
0.15999834,16.915836,-11.025266,-136.61873,-203.80075,1.510942,-2.0771742,78.7475,585000
|
| 79 |
+
0.16770422,23.81529,-10.450281,-136.6102,-202.45784,2.4908228,-1.6026392,104.45725,590000
|
| 80 |
+
0.16060975,11.204712,-8.141175,-138.22351,-201.10638,1.0275718,-2.4587026,64.14144,595000
|
| 81 |
+
0.17165644,18.739004,2.189928,-133.11069,-201.83234,1.446599,-1.850512,67.288025,600000
|
| 82 |
+
0.17220463,21.948744,2.4459026,-132.07472,-203.32074,1.2683394,-1.2681061,68.125694,605000
|
| 83 |
+
0.17768934,12.296184,-3.5817833,-137.02242,-203.4327,1.5315089,-1.7464153,49.276794,610000
|
| 84 |
+
0.15023391,18.080608,-3.1262457,-132.5472,-200.68286,1.3098089,-1.4133412,76.53503,615000
|
| 85 |
+
0.16880105,8.741852,-2.1286643,-132.96544,-202.97998,0.93677974,-1.3337348,48.964706,620000
|
| 86 |
+
0.16077618,30.118223,-6.771436,-130.54204,-203.04936,3.2418182,-3.635297,125.795715,625000
|
| 87 |
+
0.13869977,15.109611,-3.4447484,-133.04796,-204.45393,1.4143564,-1.3628802,77.19764,630000
|
| 88 |
+
0.15347365,16.388079,1.5993785,-136.12617,-205.32399,1.1236508,-1.2731829,78.8834,635000
|
| 89 |
+
0.16540056,12.137749,1.2675673,-127.464134,-205.34863,2.2671187,-2.211922,67.97961,640000
|
| 90 |
+
0.14970168,10.316218,-6.845683,-134.98578,-203.55667,1.6962473,-1.5057838,48.653736,645000
|
| 91 |
+
0.1949748,15.224373,-3.9012096,-126.91457,-203.11748,0.59780717,-0.8138679,54.26546,650000
|
| 92 |
+
0.18402833,12.316866,-5.953347,-130.21574,-203.68518,0.76065814,-0.77576476,54.51706,655000
|
| 93 |
+
0.17538443,41.37698,4.4013724,-127.33062,-203.46194,1.1691228,-0.99598217,91.17131,660000
|
| 94 |
+
0.16903983,12.355124,-2.0447662,-131.13109,-202.68234,0.7385681,-0.7438323,50.812244,665000
|
| 95 |
+
0.16570365,15.05957,-5.7362676,-128.73128,-203.78188,1.3553962,-1.4394759,58.451965,670000
|
| 96 |
+
0.17875159,16.782684,-1.2316968,-127.285255,-204.784,5.588981,-6.672088,172.5488,675000
|
| 97 |
+
0.1651623,11.102368,0.26012057,-129.87465,-201.41722,0.8314714,-0.8686829,43.432632,680000
|
| 98 |
+
0.17703238,13.513748,-4.845741,-131.01518,-203.9408,1.890545,-1.6246508,95.454285,685000
|
| 99 |
+
0.17201641,10.93647,-7.773265,-129.55884,-204.0193,0.7622489,-1.1251225,62.753445,690000
|
| 100 |
+
0.16369446,15.255335,-3.2087393,-120.86993,-203.78448,1.5005481,-1.3497791,64.14764,695000
|
| 101 |
+
0.18713434,21.277418,-0.5492825,-121.31524,-204.46474,1.2885767,-1.0083845,75.02087,700000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/online_agent_sv.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
actor/flow_loss,critic/critic_loss,critic/q_max,critic/q_mean,critic/q_min,grad/max,grad/min,grad/norm,step
|
| 2 |
+
0.20100777,9.409554,-69.87877,-177.8744,-204.56952,10.156871,-8.893482,140.8757,205000
|
| 3 |
+
0.2030812,13.464017,-59.740788,-176.18771,-203.49301,0.6195959,-0.47105342,63.705963,210000
|
| 4 |
+
0.17023364,12.263251,-57.90504,-174.65022,-203.8613,0.4514531,-0.46707118,38.107838,215000
|
| 5 |
+
0.18201995,15.194278,-57.595905,-175.04878,-204.4804,0.57863003,-0.5209974,45.85898,220000
|
| 6 |
+
0.21482798,10.721947,-62.788883,-174.35913,-204.68207,0.6177783,-0.49075928,42.487614,225000
|
| 7 |
+
0.1848709,22.483286,-46.073135,-174.1651,-204.51782,1.1910027,-1.0690478,65.86507,230000
|
| 8 |
+
0.18086866,11.235286,-55.918163,-172.9547,-204.68556,0.37382895,-0.39640066,41.033997,235000
|
| 9 |
+
0.22556049,10.152976,-62.81238,-173.63622,-204.3738,0.39822507,-0.37674218,37.1173,240000
|
| 10 |
+
0.17555308,9.554568,-58.444225,-172.61221,-205.03313,0.5940277,-0.5516616,37.41432,245000
|
| 11 |
+
0.20202735,13.335947,-48.50966,-172.95593,-204.98065,0.50040984,-0.4104112,44.45418,250000
|
| 12 |
+
0.18236683,15.440984,-33.451588,-170.57622,-205.1152,1.0633335,-1.2514275,50.95133,255000
|
| 13 |
+
0.21282479,12.19637,-23.920721,-171.91312,-204.80103,0.41326144,-0.5220463,64.220055,260000
|
| 14 |
+
0.18925047,10.774324,-56.61881,-171.2418,-205.19048,0.4044517,-0.37020415,44.610645,265000
|
| 15 |
+
0.18780795,18.316519,-18.646774,-165.85579,-205.13983,0.43577084,-0.44659805,47.765675,270000
|
| 16 |
+
0.20516685,14.699882,-20.07879,-168.44766,-204.37813,0.6552143,-0.7679565,52.021626,275000
|
| 17 |
+
0.19624431,14.928409,-15.76694,-169.90495,-205.11559,4.181205,-4.4612627,96.45013,280000
|
| 18 |
+
0.18718834,18.539236,-22.725163,-169.84744,-204.81511,3.5787728,-3.8363938,97.53497,285000
|
| 19 |
+
0.18884853,8.228202,-52.658596,-167.32303,-204.43582,0.40424532,-0.5250171,38.06241,290000
|
| 20 |
+
0.17194659,11.558407,-47.379284,-166.06587,-204.14784,2.6585126,-2.6177244,88.79571,295000
|
| 21 |
+
0.20329304,11.933761,-13.41958,-162.4458,-204.69919,0.44297963,-0.53581494,44.88457,300000
|
| 22 |
+
0.1613389,19.35588,-10.228258,-164.6559,-204.51425,2.1259723,-2.1698601,96.33703,305000
|
| 23 |
+
0.18891332,19.131544,-4.557439,-159.46823,-204.66443,0.4746132,-0.50542915,51.0682,310000
|
| 24 |
+
0.1632351,12.245697,1.5968426,-160.07527,-204.7615,0.4908134,-0.7087205,49.264454,315000
|
| 25 |
+
0.17598325,14.440491,-46.924316,-165.38487,-204.77924,0.8539426,-0.82388216,54.06479,320000
|
| 26 |
+
0.20054707,16.260023,-37.042057,-163.27727,-204.6969,1.0537571,-0.99057883,74.19384,325000
|
| 27 |
+
0.18412662,20.287693,-7.723515,-161.28021,-205.24512,0.6544641,-0.69861954,64.018555,330000
|
| 28 |
+
0.18113422,14.071883,2.470496,-160.15239,-204.98764,0.70118153,-0.48810682,63.532265,335000
|
| 29 |
+
0.17278692,10.066867,0.78192866,-156.50208,-204.8473,0.5756796,-0.56880754,50.4505,340000
|
| 30 |
+
0.18541476,16.935337,-15.702345,-157.31746,-204.37492,3.3171105,-2.8199182,84.433495,345000
|
| 31 |
+
0.18366764,11.666587,-22.472124,-157.97203,-204.2429,1.2402115,-1.0259283,51.13912,350000
|
| 32 |
+
0.1743964,7.1984215,-15.913654,-155.95833,-204.65659,0.68188596,-0.758972,51.007263,355000
|
| 33 |
+
0.21175303,18.841211,-20.607973,-159.5158,-205.31863,1.3890916,-1.4138421,62.24877,360000
|
| 34 |
+
0.18064243,9.564801,-3.5754108,-154.34062,-205.44847,1.2249285,-0.82055604,47.60972,365000
|
| 35 |
+
0.1740123,18.502813,-25.637144,-155.7119,-205.14563,1.4692957,-1.4782456,66.458496,370000
|
| 36 |
+
0.2098609,12.042827,-3.758899,-155.72098,-205.79437,0.90201515,-0.8859506,56.15162,375000
|
| 37 |
+
0.17615503,16.208109,4.60008,-153.68494,-205.9558,3.6985168,-3.8621852,93.64393,380000
|
| 38 |
+
0.18506245,13.661484,-24.66742,-152.11035,-204.80345,0.61868215,-0.6624401,47.13382,385000
|
| 39 |
+
0.16344944,17.388006,-14.055939,-151.01625,-204.46004,1.6258293,-1.6770139,83.659195,390000
|
| 40 |
+
0.15841107,17.616018,-17.341791,-148.30794,-203.26086,0.6245556,-0.6838363,55.242416,395000
|
| 41 |
+
0.15545848,24.551254,-9.772065,-149.55035,-204.40657,1.1222425,-1.1958777,79.06295,400000
|
| 42 |
+
0.18091281,12.180981,-5.245518,-147.90837,-203.43521,3.4111538,-3.6064765,93.27745,405000
|
| 43 |
+
0.16591415,34.31397,0.5574629,-147.49768,-204.17393,1.178774,-1.2150983,103.07872,410000
|
| 44 |
+
0.20231561,29.604925,-11.357351,-150.31169,-204.60204,1.3953775,-1.1974523,76.24299,415000
|
| 45 |
+
0.17641772,17.48673,-7.1269674,-148.88237,-204.25932,0.85872895,-0.9011842,53.958206,420000
|
| 46 |
+
0.18215272,20.720823,-6.716765,-141.95296,-200.65166,0.9066922,-0.7736609,83.27788,425000
|
| 47 |
+
0.20641512,19.810425,-4.849878,-148.29845,-204.91791,2.30933,-2.1597123,81.28222,430000
|
| 48 |
+
0.17660189,11.094462,-7.3228016,-144.80606,-203.25275,0.4992343,-0.44987458,51.339756,435000
|
| 49 |
+
0.19684954,14.5761385,3.3698266,-148.0756,-205.39117,0.6209063,-0.65316904,58.549694,440000
|
| 50 |
+
0.18752298,16.77013,-17.65461,-145.43347,-206.79004,2.0806866,-2.0905707,58.519016,445000
|
| 51 |
+
0.15905997,22.66004,-13.940053,-136.65092,-204.91208,0.68818146,-0.8356606,61.799004,450000
|
| 52 |
+
0.17852955,22.696243,-7.5126204,-146.60352,-204.16869,1.6004945,-2.0245695,106.26013,455000
|
| 53 |
+
0.20046319,12.400351,2.7658887,-143.369,-204.14307,0.6820656,-0.7226073,48.965046,460000
|
| 54 |
+
0.16603181,13.396224,-4.9958215,-145.32207,-204.59792,1.0521985,-1.1597939,56.790184,465000
|
| 55 |
+
0.19051006,22.577358,-8.894181,-145.17007,-203.70505,1.051367,-1.0433577,83.08147,470000
|
| 56 |
+
0.17710492,18.861845,-2.957842,-142.75897,-204.87173,0.95010775,-1.0798334,60.891502,475000
|
| 57 |
+
0.20014888,18.792406,-7.8571525,-145.55049,-205.05147,1.0315069,-1.1156279,76.44721,480000
|
| 58 |
+
0.14014131,13.498488,-8.811894,-141.95602,-205.03214,0.97438604,-0.95301956,60.211586,485000
|
| 59 |
+
0.16438508,17.622131,0.0073166937,-137.5183,-205.44365,1.804859,-2.7860637,75.53738,490000
|
| 60 |
+
0.16220123,18.137064,1.1836677,-138.26732,-206.47401,2.8542607,-3.1024394,92.50272,495000
|
| 61 |
+
0.1521937,13.130618,-6.0926414,-142.69913,-203.35548,0.9373735,-1.0258695,64.1406,500000
|
| 62 |
+
0.18573265,16.525612,-5.7103796,-143.23454,-204.5616,1.1768271,-1.1775948,80.72108,505000
|
| 63 |
+
0.19157785,22.621483,-7.923869,-138.0,-204.42947,1.0523185,-1.0264663,66.11385,510000
|
| 64 |
+
0.16532046,13.735717,-11.089387,-135.70116,-203.50761,0.6721011,-0.6336218,53.566017,515000
|
| 65 |
+
0.16647905,19.009996,-3.1124759,-141.74803,-202.44348,0.8190097,-1.4557772,65.08297,520000
|
| 66 |
+
0.16967948,17.789572,-8.616635,-140.17053,-204.66219,0.92178285,-1.001431,57.612152,525000
|
| 67 |
+
0.18110111,19.052444,-0.7262464,-134.04239,-204.0279,3.7241864,-3.8394585,111.93406,530000
|
| 68 |
+
0.2071534,11.235112,-6.123059,-135.75882,-205.55742,4.8970304,-4.633314,93.251205,535000
|
| 69 |
+
0.17416334,14.998515,-1.4488183,-139.46434,-200.9367,0.8948727,-0.9666061,62.150803,540000
|
| 70 |
+
0.17773488,10.925357,-17.1159,-143.5125,-203.01274,0.64000297,-0.5278116,50.071846,545000
|
| 71 |
+
0.15636533,13.704974,-4.5214024,-130.53934,-205.37036,0.57138234,-1.7236669,88.67557,550000
|
| 72 |
+
0.18564107,18.469059,-5.2898417,-138.99084,-203.01262,2.015253,-0.6794735,63.436623,555000
|
| 73 |
+
0.15758286,14.073359,-7.819827,-132.72684,-204.1892,7.0398135,-6.580752,192.36351,560000
|
| 74 |
+
0.17968695,18.241192,-5.2041836,-139.66605,-203.83383,0.63480955,-0.63171893,52.946182,565000
|
| 75 |
+
0.1725044,14.956375,2.2193115,-137.8896,-203.87447,0.40843022,-0.4981443,49.872967,570000
|
| 76 |
+
0.18485534,12.866968,0.69352674,-134.95142,-203.45863,0.7120311,-0.577571,48.615097,575000
|
| 77 |
+
0.1567674,12.027698,-3.3798804,-133.5681,-203.4459,1.2448539,-1.3802873,79.26493,580000
|
| 78 |
+
0.15999834,16.915836,-11.025266,-136.61873,-203.80075,1.510942,-2.0771742,78.7475,585000
|
| 79 |
+
0.16770422,23.81529,-10.450281,-136.6102,-202.45784,2.4908228,-1.6026392,104.45725,590000
|
| 80 |
+
0.16060975,11.204712,-8.141175,-138.22351,-201.10638,1.0275718,-2.4587026,64.14144,595000
|
| 81 |
+
0.17165644,18.739004,2.189928,-133.11069,-201.83234,1.446599,-1.850512,67.288025,600000
|
| 82 |
+
0.17220463,21.948744,2.4459026,-132.07472,-203.32074,1.2683394,-1.2681061,68.125694,605000
|
| 83 |
+
0.17768934,12.296184,-3.5817833,-137.02242,-203.4327,1.5315089,-1.7464153,49.276794,610000
|
| 84 |
+
0.15023391,18.080608,-3.1262457,-132.5472,-200.68286,1.3098089,-1.4133412,76.53503,615000
|
| 85 |
+
0.16880105,8.741852,-2.1286643,-132.96544,-202.97998,0.93677974,-1.3337348,48.964706,620000
|
| 86 |
+
0.16077618,30.118223,-6.771436,-130.54204,-203.04936,3.2418182,-3.635297,125.795715,625000
|
| 87 |
+
0.13869977,15.109611,-3.4447484,-133.04796,-204.45393,1.4143564,-1.3628802,77.19764,630000
|
| 88 |
+
0.15347365,16.388079,1.5993785,-136.12617,-205.32399,1.1236508,-1.2731829,78.8834,635000
|
| 89 |
+
0.16540056,12.137749,1.2675673,-127.464134,-205.34863,2.2671187,-2.211922,67.97961,640000
|
| 90 |
+
0.14970168,10.316218,-6.845683,-134.98578,-203.55667,1.6962473,-1.5057838,48.653736,645000
|
| 91 |
+
0.1949748,15.224373,-3.9012096,-126.91457,-203.11748,0.59780717,-0.8138679,54.26546,650000
|
| 92 |
+
0.18402833,12.316866,-5.953347,-130.21574,-203.68518,0.76065814,-0.77576476,54.51706,655000
|
| 93 |
+
0.17538443,41.37698,4.4013724,-127.33062,-203.46194,1.1691228,-0.99598217,91.17131,660000
|
| 94 |
+
0.16903983,12.355124,-2.0447662,-131.13109,-202.68234,0.7385681,-0.7438323,50.812244,665000
|
| 95 |
+
0.16570365,15.05957,-5.7362676,-128.73128,-203.78188,1.3553962,-1.4394759,58.451965,670000
|
| 96 |
+
0.17875159,16.782684,-1.2316968,-127.285255,-204.784,5.588981,-6.672088,172.5488,675000
|
| 97 |
+
0.1651623,11.102368,0.26012057,-129.87465,-201.41722,0.8314714,-0.8686829,43.432632,680000
|
| 98 |
+
0.17703238,13.513748,-4.845741,-131.01518,-203.9408,1.890545,-1.6246508,95.454285,685000
|
| 99 |
+
0.17201641,10.93647,-7.773265,-129.55884,-204.0193,0.7622489,-1.1251225,62.753445,690000
|
| 100 |
+
0.16369446,15.255335,-3.2087393,-120.86993,-203.78448,1.5005481,-1.3497791,64.14764,695000
|
| 101 |
+
0.18713434,21.277418,-0.5492825,-121.31524,-204.46474,1.2885767,-1.0083845,75.02087,700000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_250000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa6ab4f22fd5f7a1a2b55cbc1ea6e8c77c1f8aabd2c5bd910a141078b7311180
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_300000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08ab9e18ed449ccef601bf6070a67a43b2fc6e0a4533f909ec5d0812aa8d7980
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_350000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3bf2c28a06a61757a87ef76816558a7a1cc08f449a8ed487c3631e5dd47228a
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_400000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fca9dbe8843833d6316108dcea9979ac39c932cd615c4d0927b34805cbf7e9c8
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_450000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f58052598b71457ab61665662225ce656fb6a69842256573d83326c5af4e90e
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_500000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:900071ae37cde1e64aa2a1ada1035813caa8fd979eb060e4bfaa0b2df2e42f96
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_550000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99b1ff8b3b7457b3610c4159ba699f335ad4a7696bad5a1bcca980c6c7f18fe5
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_600000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f664ec57fec8fdde86c497b5ee7c6674f0c3068cfa51a89df120d616dffb300b
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_650000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:055c34a716a90e9748bf62231ca03fa00f12bf9d5d5896196872217285697d47
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/params_700000.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06ed72788ad62df3cef9f1f4ecde9154cff590c66741996aebd1b35fe5a15a34
|
| 3 |
+
size 218098303
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/progress.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
online,500000
|
O2O-w-diff-ckpts/cube-double-play-singletask-task2-v0/cgql/20260318_134158/token.tk
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
https://wandb.ai/tiredsheep-national-taiwan-university/qam-finetune-OfflineRL/runs/89b18713
|